Diagnostic Radiography Technology Department, Faculty of Applied Medical Sciences, King Abdul-Aziz University, Jeddah, Saudi Arabia.
Medical Image Optimization and Perception Group (MIOPeG), Faculty of Medicine and Health, The University of Sydney, Campus C4 75 East Street, Sydney, NSW 2141, Australia.
Radiol Phys Technol. 2021 Sep;14(3):248-261. doi: 10.1007/s12194-021-00622-6. Epub 2021 Jun 2.
Radiomic features from mammograms have been shown to predict breast cancer (BC) risk; however, their contribution to BC characteristics has not yet been explored. This study included 184 women with BC between January 2012 and April 2017. A set of 33 global radiomic features were extracted from the ipsilateral breast mammogram. Associations between radiomic features and BC characteristics were investigated by univariate logistic regression analysis, and receiver-operating characteristic curve analysis was employed to evaluate the predictive performance of radiomic features. Histogram-based features (mean, 70th percentile, and 30th percentile) weakly differentiated progesterone status and tumor size (AUC range: 0.627-0.652, p ≤ 0.007). One gray level run length matrix (GLRLM)-based feature achieved an AUC of 0.68 in discriminating lymph-node status, and the fractal dimension achieved an AUC of 0.65 in predicting tumor size. After stratifying by age at BC diagnosis and baseline percent density (PD), the average predictive performance of the abovementioned features improved from 0.652 to 0.707 for baseline PD adjustment, and from 0.652 to 0.674 for age at BC diagnosis. Higher predictive performances were found for GLRLM-based features in predicting lymph-node status among younger women with high baseline PD (AUC range: 0.710-0.863), and for fractal features in predicting tumor size among patients with low PD (AUC: 0.704). Global radiomic features from the ipsilateral breast mammogram can predict lymph-node status and tumor size among certain categories of women and should be considered as a non-invasive tool for clinical decision-making in BC-affected women and for forecasting disease progression.
乳腺 X 线摄影的放射组学特征已被证明可预测乳腺癌 (BC) 风险；然而，它们对 BC 特征的贡献尚未得到探索。本研究纳入了 2012 年 1 月至 2017 年 4 月期间的 184 名 BC 女性患者。从患侧乳腺 X 线摄影片中提取了一组 33 个全局放射组学特征。通过单变量逻辑回归分析研究放射组学特征与 BC 特征之间的关联，并采用受试者工作特征曲线分析评估放射组学特征的预测性能。基于直方图的特征（平均值、第 70 百分位数和第 30 百分位数）可区分孕激素状态和肿瘤大小（AUC 范围：0.627-0.652，p≤0.007）。一个灰度游程长度矩阵 (GLRLM) 特征在区分淋巴结状态方面的 AUC 为 0.68，分形维数在预测肿瘤大小方面的 AUC 为 0.65。对 BC 诊断时的年龄和基线密度（PD）进行分层后，上述特征的平均预测性能从基线 PD 调整后的 0.652 提高到 0.707，从 BC 诊断时的年龄调整后的 0.652 提高到 0.674。在基线 PD 较高的年轻女性中，GLRLM 特征在预测淋巴结状态方面具有更高的预测性能（AUC 范围：0.710-0.863），在 PD 较低的患者中，分形特征在预测肿瘤大小方面具有更高的预测性能（AUC：0.704）。患侧乳腺 X 线摄影的全局放射组学特征可预测某些类别的女性的淋巴结状态和肿瘤大小，可作为 BC 女性临床决策和预测疾病进展的非侵入性工具。
